On Sun, May 29, 2011 at 9:27 PM, Tom Lane <tgl@sss.pgh.pa.us> wrote:
> Pavan Deolasee <pavan.deolasee@gmail.com> writes:
>> On Sun, May 29, 2011 at 8:10 PM, Tom Lane <tgl@sss.pgh.pa.us> wrote:
>>> That would require proof, not just suggestion. Skipping pages will
>>> defeat the OS read-ahead algorithm, and so could easily cost more than
>>> reading them.
>
>> My worry is what we have right now is also based on just assumptions
>> and gut feelings rather than any numbers.
>
> So go collect some numbers.
>
I am sorry if I sounded terse above. But my gripe is that sometimes we
are too reluctant to listen to ideas and insist on producing some hard
numbers first which might take significant efforts. But we are not
equally strict when such changes are introduced initially. For
example, in this particular case, the change was introduced after this
discussion:
http://archives.postgresql.org/pgsql-hackers/2008-12/msg01316.php
Heikki suggested 20, Simon proposed 32 to make it a power of 2. But
why not 16 ? Thats closer to 16 than 32. And Greg yesterday said, 8 is
a better number based on his testings.
May be a performance build farm as being discussed is the solution
where we can throw some simple patches and see if something helps or
not.
Thanks,
Pavan
--
Pavan Deolasee
EnterpriseDB http://www.enterprisedb.com